Open AccessResearch on Tower Bolt Identification Technology Based on Convolution Network
Author(s) -
Liang Ge,
Jing Xu,
Weiping Xiao,
Rong Jin Hou,
Chang Jun Shi,
GaoYi Jia
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 - 10.1088/1742-6596/1852/2/022055
Subject(s) - identification (biology) , convolution (computer science) , computer science , residual , tower , process (computing) , artificial intelligence , image (mathematics) , convolutional neural network , scheme (mathematics) , low resolution , resolution (logic) , pattern recognition (psychology) , computer vision , high resolution , algorithm , artificial neural network , engineering , structural engineering , mathematics , mathematical analysis , botany , remote sensing , biology , geology , operating system
Aiming at the fact that tower bolts are easily affected by factors such as occlusion during the identification process, an improved FasterR-CNN bolt identification method is proposed. In this method, in view of the small size of the detection target and the low resolution of the image, a residual network is added to the traditional FasterR-CNN to improve the efficiency of image recognition. Finally, the above scheme was proved through verification. The result shows that the above method is feasible.