Research On The Enhancement Algorithm Of Low-light Level Remote Sensing Image Based On Deep Fully Convolutional Neural Network

With the continuous advancement of Internet technology,Image Enhancement Processing Technology plays an increasingly important role in military,remote sensing,astronomy and other fields in the current international situation.How does the remote sensor realize real-time monitoring of the nighttime to the ground?This is inseparable from the rapid development of image processing technology.Image Enhancement and Denoising Technology is an indispensable pre-processing part of the image processing process.However,when low-light sensor is used in the morning dusk and dawn,the captured images have characteristics of low contrast,low-brightness and low signal-to-noise ratio,which severely restricts the identification and interpretation of ground objects.Traditional Low-Light Image Enhancement Algorithms such as histogram equalization,gamma conversion,and contrast limited adaptive histogram equalization algorithm and so on can enhance the low-light remote sensing image and solve the problem of contrast enhancement,but the noise amplification effect brought by the enhancement will degrade the signal-to-noise ratio of the enhanced image.Therefore,in view of this problem,this paper proposes a theoretical and experimental research based on data-driven Low-Light Remote Sensing Image Enhancement Algorithm.First of all,lots of low-light raw image data pairs corresponding to very low illumination are captured.Then these raw image data are used to train a deep Fully-Convolutional neural network composed of an Encoder-Decoder structure.After that,the low-light remote sensing images could be enhanced by pre-trained net structure.The numerical results demonstrate that the Fully-Convolutional neural network based on Enhancement Algorithm greatly improves the brightness and the contrast of low-light images compared with the Traditional Enhancement Algorithms while a high enough signal-to-noise ratio could be preserved,which will make interpretation and identification much easier.At the same time,it also enhances the effective segmentation and recognition of low-light remote sensing images.