Motion deblurring algorithm for wind power inspection images based on Ghostnet and SE attention mechanism

Autor: Ruxin Gao, Tengfei Wang
Jazyk: angličtina
Rok vydání: 2023
Předmět:
Zdroj: IET Image Processing, Vol 17, Iss 1, Pp 291-300 (2023)
Druh dokumentu: article
ISSN: 1751-9667
1751-9659
DOI: 10.1049/ipr2.12634
Popis: Abstract Aiming at the problem of motion blur in the inspection image of wind power generation equipment, an improved fast motion blur removal method based on deblurganv2 is proposed in this paper. Firstly, according to the characteristics of disparate local motion blur degrees and different global motion blur directions of the wind power inspection image, the real wind power fuzzy image data set is collected and produced. Secondly, according to the characteristics of the single background of the wind power inspection image and the requirements of fast and effective processing, the lightweight network Ghostnet is redesigned as the backbone network of the Deblurganv2 generator to reduce the number of network parameters and calculations. Finally, five SE channel attention mechanism layers are added to GhostNet to strengthen feature extraction, and the upsampling process is optimized through bilinear interpolation, to improve the deblurring performance of the wind power inspection image. The experimental results show that compared with other algorithms, the proposed algorithm has a higher peak signal‐to‐noise ratio and structural similarity, the network model parameters are compressed to 6.1 MB, and the reasoning speed is improved to 0.42 s.
Databáze: Directory of Open Access Journals
Externí odkaz: