Research on UAV image denoising effect based on improved Wavelet Threshold of BEMD

Aiming at the noise generated by external or internal factors reduces the sharpness of unmanned aerial vehicle (UAV) images, an improved bi-dimensional empirical mode decomposition (BEMD) de-noising algorithm is proposed to solve the problem. Firstly, an intrinsic mode function (IMF) is obtained aft...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of physics. Conference series Ročník 1437; číslo 1; s. 12032 - 12043
Hlavní autoři: Pingjuan, NIU, Xueru, MA, Run, MAO, Pan, Jie, Wang, Shan, Hao, Shi, She, Huanlin
Médium: Journal Article
Jazyk:angličtina
Vydáno: Bristol IOP Publishing 01.01.2020
Témata:
Algorithms
Decomposition
Noise reduction
Particle swarm optimization
Physics
Sharpness
Signal to noise ratio
Unmanned aerial vehicles
Wave attenuation
Wavelet transforms
ISSN:1742-6588, 1742-6596
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Aiming at the noise generated by external or internal factors reduces the sharpness of unmanned aerial vehicle (UAV) images, an improved bi-dimensional empirical mode decomposition (BEMD) de-noising algorithm is proposed to solve the problem. Firstly, an intrinsic mode function (IMF) is obtained after BEMD decomposition of noisy image, and then the high frequency apply particle swarm optimization (PSO) after wavelet decomposition to the high-frequency IMF to obtain the optimal threshold filtering. As for the low frequency, it is filtered by the exponential attenuation threshold algorithm of wavelet semi-soft threshold. Finally, the filtered both high-frequency and low-frequency IMF are reconstructed after inverse wavelet transformation. This algorithm is applied to the processing of UAV images, and compared with the traditional UAV image denoising method and the advanced UAV image denoising method. Simulation results demonstrate that the proposed denoising method outperforms other de-noising methods in terms of peak signal-to-noise ratio and mean square error.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1437/1/012032