Pointer meter recognition in UAV inspection of overhead transmission lines. (August 2022)

• Record Type: Journal Article
• Authors: Wang, Chen; Pei, Huikun; Tang, Guanghui; Liu, Bingcai; Liu, Zhixiong
• Is Part Of: Energy reports. Volume 8(2022)Supplement 5
• Page Start: 243
• Page End: 250
• Publication Date: 2022-08
• Subjects: Arrest counter -- UAV inspection -- Deep learning -- Pointer meter recognition; Power resources -- Periodicals; Energy industries -- Periodicals; Power resources; Periodicals; Electronic journals; 621.04205
• DOI: 10.1016/j.egyr.2022.02.108
• Languages: English
• ISSNs: 2352-4847

Abstract

Abstract: At present, UAV (unmanned aerial vehicle) inspection has been widely used in the operation and maintenance of overhead transmission lines. However, the instrument indications of overhead lines are reading usually by climbing artificially or manual reading from UAV videos. Compared with pointer meter recognition applications in other fields, the pointer meter recognition in UAV inspection is more difficult, due to its various complex photo conditions. In this paper, the intelligent recognition system of pointer arrester counter in UAV inspection of transmission lines is studied, a pointer meter recognition method based on deep learning is proposed, which can effectively identify meter indications under various brightness levels and camera angles in inspection videos.