Real-time fan blade image segmentation method and system

Abstract

The invention provides a real-time fan blade image segmentation method and system, and the method comprises the steps: constructing a deep semantic segmentation network based on a dual-path information fusion structure, and the deep semantic segmentation network comprises a high-resolution branch, a low-resolution branch, a feature fusion module, a space attention module and a segmentation module; images in the fan blade image data sample set are input into the network, and feature extraction is carried out through the lightweight dense connection module in each branch; acquiring context information of a feature map output by the low-resolution branch through a space attention module, performing feature fusion on the information output by the two branches through a feature fusion module, and acquiring an initial segmentation result through a segmentation module; and carrying out iterative training on the segmentation network until the precision of the segmentation result reaches a preset threshold value, inputting the to-be-segmented image into the trained segmentation network, and obtaining an image segmentation result output by the network. According to the method, the real-time performance of image segmentation is improved while the segmentation precision is ensured.

Description

technical field [0001] The present application relates to the technical field of image segmentation, and in particular, to a real-time fan blade image segmentation method and system. Background technique [0002] With the development of wind power generation technology, the popularity of wind power generation through wind turbines is getting higher and higher. In order to ensure the normal operation of the wind turbine, it is necessary to detect the fan blades, so that the corresponding measures can be taken in time when the fan blades are damaged. At present, the inspection of wind turbine blades based on drones generally inputs the blade images containing background information captured by drones into the blade image recognition model for calculation. However, due to the complex location environment of the wind turbine, the background information is easy to interfere. Recognition effect of leaf images. Therefore, it is necessary to first segment the fan blades and the ba...

AI Technical Summary

Problems solved by technology

[0007] For this reason, the first purpose of this application is to propose a real-time fan blade image segmentation method, which solves the problems caused by the amount of parameters and calculations caused by the existing semantic segmentation network in the face of large and high-resolution UAV images. The problem of low efficiency of segmentation algorithm

Images