Blade automatic detection and tracking method, system, device and storage medium

Abstract

The present invention provides a blade automatic detection and tracking method, system, equipment and storage medium, which are used to track fan blades through a drone. A cloud platform is set on the drone, and the camera angle is controlled by the cloud platform, including: The camera collects the leaf video file, detects at least one frame of leaf image in the leaf video file, and extracts the side of the leaf area in at least one frame of the leaf image; according to the side of the leaf area, multiple frames adjacent in time in the leaf video file The side of the leaf area in the leaf image is tracked and detected; the midpoint of the line connecting the midpoints of the leaf sides in the multi-frame leaf image is determined as the center point of the leaf area in each frame of the leaf image, and according to the center point of the leaf area and the corresponding The offset between the centers of the frame leaf images adjusts the gimbal so that the center point of the leaf area moves toward the center of the corresponding frame leaf images. The invention can make the blade area close to the center of the blade image as much as possible, thereby improving the image shooting quality.

Description

technical field [0001] The invention relates to fan blade detection, in particular to a blade automatic detection and tracking method, system, equipment and storage medium. Background technique [0002] A wind turbine is a power device that converts wind energy into mechanical work, which drives the rotor to rotate, and finally outputs alternating current. Wind turbines generally consist of components such as blades, generators, steering devices, towers, speed limiting safety mechanisms, and energy storage devices. [0003] During the long-term operation of the wind turbine, the surface of the blade will show various damages, such as damage to the protective film of the blade, peeling of the paint on the blade, freezing of the blade, cracks on the blade, and oil pollution on the blade. [0004] At present, when detecting damage on the surface of the blade, it is usually used to manually climb up the wind turbine for detection, which not only consumes a lot of manpower, but ...

AI Technical Summary

Problems solved by technology

However, when the drone is loaded with a camera for work, GPS is used for positioning, but there are errors in GPS positioning and certain errors when modeling the flight path of the drone. There is a situation where it deviates from the shooting screen, so it is necessary to keep tracking the leaves

Images