The sensing light source of the line scan camera cannot be fully exposed in a low light environment due to the extremely small number of photons and high noise,which leads to a reduction in image quality.A multi-scale...The sensing light source of the line scan camera cannot be fully exposed in a low light environment due to the extremely small number of photons and high noise,which leads to a reduction in image quality.A multi-scale fusion residual encoder-decoder(FRED)was proposed to solve the problem.By directly learning the end-to-end mapping between light and dark images,FRED can enhance the image’s brightness with the details and colors of the original image fully restored.A residual block(RB)was added to the network structure to increase feature diversity and speed up network training.Moreover,the addition of a dense context feature aggregation module(DCFAM)made up for the deficiency of spatial information in the deep network by aggregating the context’s global multi-scale features.The experimental results show that the FRED is superior to most other algorithms in visual effect and quantitative evaluation of peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM).For the factor that FRED can restore the brightness of images while representing the edge and color of the image effectively,a satisfactory visual quality is obtained under the enhancement of low-light.展开更多
基金supported by the National Key Research and Development Project(2019YFC0121502)the Graduate Innovation Fund Project of Xi’an University of Posts and Telecommunications(CXJJLY2019062)the Key Laboratory of Network Data Analysis and Intelligent Processing of Shaanxi Province。
文摘The sensing light source of the line scan camera cannot be fully exposed in a low light environment due to the extremely small number of photons and high noise,which leads to a reduction in image quality.A multi-scale fusion residual encoder-decoder(FRED)was proposed to solve the problem.By directly learning the end-to-end mapping between light and dark images,FRED can enhance the image’s brightness with the details and colors of the original image fully restored.A residual block(RB)was added to the network structure to increase feature diversity and speed up network training.Moreover,the addition of a dense context feature aggregation module(DCFAM)made up for the deficiency of spatial information in the deep network by aggregating the context’s global multi-scale features.The experimental results show that the FRED is superior to most other algorithms in visual effect and quantitative evaluation of peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM).For the factor that FRED can restore the brightness of images while representing the edge and color of the image effectively,a satisfactory visual quality is obtained under the enhancement of low-light.
