基于深度卷积神经网络的图像帧间补偿研究

Research on Image Interframe Compensation Based on Deep Convolutional Neural Network

由于图像分辨率低,传输过程中容易出现图像丢失、不清晰现象。针对上述问题,提出一种深度卷积神经网络算法实现图像帧间补偿。首先依据深度卷积神经网络构建图像帧间补偿模型,其次采用稀疏自编码与线性解码方式提取出该补偿模型的图像特征,再通过多层卷积神经网络对图像特征做映射处理,最后根据稀疏算法重建图像帧分辨率,使图像帧间得到补偿。实验结果表明,基于深度卷积神经网络的图像帧补偿实训可以有效提高图像帧分辨率,解决图像丢失问题,实现了图像高清晰化。

Due to the low image resolution and image loss during transmission,this article proposed an algorithm based on deep convolution neural network to realize image inter-frame compensation.Firstly,the image inter-frame compensation model was constructed based on the deep convolution neural network.Secondly,image features of this compensation model were extracted by the way of sparse self-encoding and linear decoding.Then,the image features were mapped by multi-layer convolution neural network.Finally,the image frame resolution was reconstructed by the sparse algorithm,so that the inter-frame compensation of image was achieved.Simulation results show that the image frame compensation training based on deep convolution neural network can effectively improve the resolution ratio of image frame,so that the image loss is solved and the high clarity of image is achieved.