Open AccessResearch on Image Recognition Algorithm Technology for Power Line detection
Author(s) -
Dong Wang,
Tuofu Zhu,
Aoyu Xie,
Nian Fang,
Hongliang Liu
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1732/1/012082
Subject(s) - aerial image , line (geometry) , image (mathematics) , energy (signal processing) , computer science , power (physics) , algorithm , artificial intelligence , computer vision , function (biology) , reliability (semiconductor) , feature detection (computer vision) , image processing , mathematics , statistics , physics , geometry , quantum mechanics , evolutionary biology , biology
Based on the analysis of power line features in aerial images, this paper proposes a power line detection algorithm for aerial images based on adjustable direction filtering. The thesis first performs directional filtering on the image and calculates its directional energy function and ridge energy function, then combines the image local and global information to fit the line segments in the image, and finally verifies the reliability and real-time performance of the algorithm through experimental methods. The calculation of this algorithm is about half of the ED Lines algorithm. Experimental results show that the algorithm can detect power lines in aerial images better, and the algorithm is not complicated, which is suitable for real-time detection of power lines.