Unmanned aerial vehicle autonomous inspection method and system based on machine vision

Abstract

The invention discloses an unmanned aerial vehicle autonomous inspection method based on machine vision, and belongs to the technical field of unmanned aerial vehicle autonomous inspection, and the autonomous inspection method specifically comprises the following steps: 1, generating a path; step 2, task scheduling; step 3, positioning inspection; step 4, routing inspection micro-control; 5, carrying out regional inspection circulation; according to the method, the unmanned aerial vehicle autonomous routing inspection path is generated through three-dimensional modeling and key point segmentation, single modeling is only performed on the same type of power transmission line towers, and compared with a conventional unmanned aerial vehicle autonomous routing inspection method, large-scale modeling does not need to be performed on each power transmission line tower in different environments, so that the modeling cost is reduced, and the modeling efficiency is improved. Meanwhile, aircraft micro-control is carried out based on fuzzy reasoning, and inspection scenes in different environments can be met; in addition, the optimal flight attitude of the unmanned aerial vehicle is obtained based on multi-type parameters and fuzzy reasoning, the flight precision can be improved, the collected target image is located in the center of the image, and the false detection rate and the omission ratio of the defects of the electric power tower are reduced.

Description

technical field [0001] The invention relates to the technical field of autonomous inspection of unmanned aerial vehicles, in particular to a method and system for autonomous inspection of unmanned aerial vehicles based on machine vision. Background technique [0002] The safety and stability of power towers is one of the important factors to ensure stable power supply. The working environment of power transmission equipment is relatively harsh, and it is difficult to avoid damage during operation, resulting in defects, which may threaten the normal operation of the power system; in order to ensure the power system The stable operation of the power tower must be regularly inspected and maintained; now, with the development of UAV technology and image processing technology, the UAV inspection technology based on machine vision has become the most popular patrol inspection technology in the power grid system. Inspection method; At present, UAV power inspection still mainly reli...

AI Technical Summary

Problems solved by technology

[0002] The safety and stability of power towers is one of the important factors to ensure the stable supply of power. The working environment of power transmission equipment is relatively harsh, and it is difficult to avoid damage during operation, resulting in defects, which may threaten the normal operation of the power system; in order to ensure the power system The stable operation of the power tower must be inspected and maintained regularly; nowadays, with the development of UAV technology and image processing technology, the UAV inspection technology based on machine vision has become the most popular inspection method in the power grid system. At present, UAV power inspections still mainly rely on skilled UAV operators to manually operate UAVs to carry out inspections. Compared with the previous manual inspections, although the inspection efficiency has been greatly improved, However, the degree of automation still needs to be improved; although, some UAV autonomous inspection methods have appeared; The method of manually setting track points in the three-dimensional model of the channel or automatically generating track points through software algorithms can obtain the inspection flight path of the UAV, and control the UAV to patrol according to the flight path during inspection; although this method It has the advantages of automatic inspection, but the cost is high, and it depends on the absolute geographic location coordinates. In the actual environment, there are prone to flight deviations, resulting in low flight accuracy, which leads to the collected target images often being drawn or the defects are not obvious. , which will easily lead to high false detection rate and missed detection rate of power pole and tower defects; therefore, we propose a method and system for autonomous inspection of drones based on machine vision

Images