Open AccessImprovement of Faster-RCNN Detection Algorithms for Small Size Line Accessory Equipment
Author(s) -
Qi Wang,
Zhenli Wang,
Jianxiang Li,
Yang Yuechen,
Piyu Liu
Publication year - 2020
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 - 10.1088/1742-6596/1453/1/012007
Subject(s) - computer science , convolution (computer science) , artificial intelligence , algorithm , image (mathematics) , pattern recognition (psychology) , residual , backbone network , line (geometry) , computer vision , mathematics , artificial neural network , computer network , geometry
Aiming at the problem that the image of patrol inspection is affected by angle and distance, the target of small size accessory equipment in the image is small, and the recognition rate of current algorithm is low. An improved Faster-RCNN detection algorithm for small size accessory equipment of patrol image is proposed. By adjusting the structure of Faster-RCNN network, we can overcome the shortcomings of the current algorithm. Firstly, the deep residual network ResNet50 is used to replace VGG16 network. At the same time, the bottom and high-level features of convolution network are applied to the selection of candidate regions, so as to improve the utilization of effective information of targets, and then to improve the detection precision of small-sized targets. The results show that the detection accuracy of the improved Faster-RCNN model is 4.2% higher than that of the original algorithm.