| At present,UAV technology has been widely used in transmission line inspection.Its camera takes pictures of key components along the transmission line,so as to obtain a large number of aerial images.If only use manual operation to identify and determine the faults in these aerial images,it will not only take a lot of time,but also have a poor effect.Therefore,replacing human eyes with computer vision technology to identify and locate the faults of some objects in pictures can not only reduce the work intensity of inspectors,but also avoid the misjudgment caused by the subjective consciousness of some inspectors.This paper identifies and locates four common faults in the key components of transmission lines,which provides a basis for realizing the intelligence of power patrol inspection in the later stage.Firstly,this paper introduces the research status of UAV inspection and computer vision at home and abroad,and analyzes the advantages and disadvantages of the existing fault identification algorithms for transmission line key components.Secondly,for the faults of the four main components of transmission lines,such as insulator flashover,insulator bunch-drop,foreign object on transmission line and bird’s nest on the transmission tower.To identify and locate the fault,the multi-saliency aggregation insulator flashover fault identification algorithm,the insulator fault identification algorithm based on spatial morphological characteristics,the fault identification algorithm for foreign body hanging on transmission line based on LSD and multi-features and the fault identification algorithm for bird’s nest on transmission tower based on Harris corner detection and morphological processing are proposed respectively.And compare and analyze the proposed algorithm with existing algorithms.The results show that the proposed fault identification algorithms can effectively identify and locate the fault location,and has high fault recognition rate and accuracy. |
PDF Full Text Request