Frequency-Based Haze and Rain Removal Network (FHRR-Net) with Deep Convolutional Encoder-Decoder

Applied Sciences

DongHwan Kim¹  DongWon Kim²  WooJin Ahn³  MyoTaeg Lim³  TaeKoo Kang⁴ 

[1] Department of Automotive Convergence, Korea University, Seoul 02841, Korea;Department of Digital Electronics, Inha Technical College, Incheon 22212, Korea;Department of Electrical Engineering, Korea University, Seoul 02841, Korea;Department of Human Intelligence and Robot Engineering, Sangmyung University, Cheonan 31066, Korea;

关键词: encoder-decoder network;    dilated convolution;    image restoration;    guided filter;    dehaze;    derain;   

DOI  :  10.3390/app11062873

来源: DOAJ

【 摘 要 】

Removing haze or rain is one of the difficult problems in computer vision applications. On real-world road images, haze and rain often occur together, but traditional methods cannot solve this imaging problem. To address rain and haze problems simultaneously, we present a robust network-based framework consisting of three steps: image decomposition using guided filters, a frequency-based haze and rain removal network (FHRR-Net), and image restoration based on an atmospheric scattering model using predicted transmission maps and predicted rain-removed images. We demonstrate FHRR-Net’s capabilities with synthesized and real-world road images. Experimental results show that our trained framework has superior performance on synthesized and real-world road test images compared with state-of-the-art methods. We use PSNR (peak signal-to-noise) and SSIM (structural similarity index) indicators to evaluate our model quantitatively, showing that our methods have the highest PSNR and SSIM values. Furthermore, we demonstrate through experiments that our method is useful in real-world vision applications.

【 授权许可】

Unknown