A lightweight model for blade tip image enhancement in helicopter rotor motion parameter measurement system

Abstract

The helicopter rotor torsion angle is an important motion parameter of a helicopter rotor, which is helpful for the design of helicopter rotor system. The stereoscopic vision-based method measures the torsion angle by computing the directions of the blade tips in the blade tip images. However, the captured blade tip images suffer from blurring and underexposure, which affect the measurement accuracy. To this end, a lightweight deep model is proposed to improve the image quality. In addition, a blade tip image dataset is proposed to train the network. Corresponding experiments demonstrate the effectiveness of the proposed model. Compared to competitive methods, our model stands out with fewer parameters and faster inference time.