Unmanned aerial vehicle autonomous inspection method based on RTK high-precision positioning and machine vision fusion
A technology of machine vision and positioning method, which is applied in the direction of vehicle position/route/height control, instrument, and use feedback control, etc. In order to solve problems such as slightly poor accuracy, it can achieve the effect of taking into account the inspection efficiency and inspection accuracy, reducing the accuracy error of waypoints, and improving the inspection speed
Active Publication Date: 2021-04-27
JIANGSU FRONTIER ELECTRIC TECH +1
View PDF15 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Some inspection targets occupy a large frame in the photo, and the vertical height accuracy of the drone may be slightly poor, which may lead to incomplete photos
Furthermore, since the UAV has a certain position deviation when it reaches each hover position during the inspection process, the reflection in the photo will cause the target device to deviate from the lens acquisition range, resulting in data acquisition failure
There is a need for an autonomous inspection method for drones to solve the problems of low intelligence in existing drone inspections, complete reliance on manual operations, and high requirements for the professional level of drone pilots.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0073]In order to solve the existing drone inspection, it is completely manually operated, and the professional level of the drone flying is required to require higher problems, and the UAV autonomous inspection technology based on RTK high-precision navigation is proposed. Artificial intervention during the inspection process, to maximize the ability of drone independent inspection. During the drone inspection process, you need to solve the following problems: first, track selection; how to collect the route information of the transmission line, obtain critical track route, reduce the redundant road point, will determine the drone autonomy The efficiency and safety of the inspection. Second, localization control; how to ensure that the drone is accurately flying along the route, control the drone to take photos in the equipment camera point, determines the quality of the drone independent inspection task, and even decides the subsequent state perception and defect identification Co...
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
Login to View More Abstract
The invention provides an unmanned aerial vehicle autonomous inspection method based on RTK high-precision positioning and machine vision fusion. According to the method, route selection can be carried out before automatic inspection of an unmanned aerial vehicle, redundant point filtering is carried out through a track screening method based on key points and track included angles, and an optimized inspection route is output; when the unmanned aerial vehicle flies to be close to a photographing point, the unmanned aerial vehicle adjusts the spatial position of the unmanned aerial vehicle through an RTK-based high-precision positioning method so as to accurately reach the photographing point; and the unmanned aerial vehicle controls a holder to rotate before photographing through a dynamic optimization positioning method based on the difference characteristics of an inspection object, and performs photographing after a target equipment picture is located at the center of the picture. According to the unmanned aerial vehicle autonomous inspection method, the problems of air route collection and positioning optimization are solved, the inspection efficiency and the inspection accuracy are both considered in the process from air route learning to autonomous inspection, and a high-efficiency solution for refined inspection is provided.
Description
Technical field[0001]The present invention relates to the field of automatic automatic control technology, and in particular, an autonomous inspection method based on RTK high-precision positioning and machine visual fusion.Background technique[0002]The drone is traversed by the known route points to complete the inspection task. The set of route points includes redundancy, so the efficiency and security of the autonomous inspection of the drone will be affected. After the drone arrived at the inspection point, it will execute the PTZ focus, take pictures of the target but the road point accuracy is not enough to lead the shooting accuracy. At the same time, the size of the power device is different, the shooting requirements are different, during normalized operation, the characteristics of different devices determine the size in the picture. Some inspection goals take up a large number of frames in the photo, and the vertical height accuracy of the drone may lead to incomplete sho...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G05D1/10G05D3/12G01C21/20
CPCG01C21/20G05D1/0094G05D1/101G05D3/12
Inventor 黄郑王红星翟学锋陈晟王永强姜海波
Owner JIANGSU FRONTIER ELECTRIC TECH