基于深度学习多帧海面图像超分辨算法研究

Research on Multi-Frame Sea Surface Image Super Resolution Algorithm Based on Deep Learning

近年来,深度学习在图像超分辨重建方面表现出色。然而,由于复杂的海洋环境,传统的图像超分辨算法存在着调节参数困难等问题,单帧图像超分辨率算法亦存在病态的恢复,生成的像素点具有不确定性。提出了一种多帧图像的超分辨重建算法以用于海面图像重建研究,利用深度学习中的卷积神经网络来学习多帧低分辨率图像与高分辨率图像之间的映射关系,从而实现超分辨率重建。同时,由于海洋监测成像系统需要更多的高频信息来判别目标及锁定轮廓,提出应用残差网络框架来改善网络重建图像的质量,恢复更多的高频信息,丰富图像的细节。实验结果表明,所提算法具有较好的图像重建能力,与其他方法相比具有较好的主客观评价结果。

In recent years,deep learning has made a great achievement in image super-resolution reconstruction.Due to the complex ocean environment,the traditional image super-resolution algorithm has some problems,such as the difficulty in adjusting parameters.In addition,the single frame image super-resolution algorithm has an ill conditioned recovery and the generated pixels are uncertain.In this paper,a super-resolution reconstruction algorithm of multi-frame images is proposed for the study of sea surface image reconstruction.The convolution neural network in deep learning is used to learn the mapping relationship between multi-frame low-resolution images and high-resolution images,so as to realize super-resolution reconstruction.At the same time,because the ocean monitoring imaging system needs more high-frequency information to identify the target and lock contour,the residual network framework is proposed to improve the quality of network reconstruction images,recover more high-frequency information and enrich the image details.The experimental results show that the proposed algorithm has a better image reconstruction ability and better subjective and objective evaluation results compared with other methods.