当前位置: X-MOL 学术Wirel. Commun. Mob. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Superresolution Reconstruction of Video Based on Efficient Subpixel Convolutional Neural Network for Urban Computing
Wireless Communications and Mobile Computing ( IF 2.146 ) Pub Date : 2020-07-11 , DOI: 10.1155/2020/8865110
Jie Shen 1 , Mengxi Xu 2 , Xinyu Du 1, 3 , Yunbo Xiong 1
Affiliation  

Video surveillance is an important data source of urban computing and intelligence. The low resolution of many existing video surveillance devices affects the efficiency of urban computing and intelligence. Therefore, improving the resolution of video surveillance is one of the important tasks of urban computing and intelligence. In this paper, the resolution of video is improved by superresolution reconstruction based on a learning method. Different from the superresolution reconstruction of static images, the superresolution reconstruction of video is characterized by the application of motion information. However, there are few studies in this area so far. Aimed at fully exploring motion information to improve the superresolution of video, this paper proposes a superresolution reconstruction method based on an efficient subpixel convolutional neural network, where the optical flow is introduced in the deep learning network. Fusing the optical flow features between successive frames can compensate for information in frames and generate high-quality superresolution results. In addition, in order to improve the superresolution, a superpixel convolution layer is added after the deep convolution network. Finally, experimental evaluations demonstrate the satisfying performance of our method compared with previous methods and other deep learning networks; our method is more efficient.

中文翻译:

基于高效亚像素卷积神经网络的城市视频超分辨率重建

视频监控是城市计算和情报的重要数据源。许多现有视频监视设备的低分辨率会影响城市计算和智能的效率。因此,提高视频监控的分辨率是城市计算和智能的重要任务之一。本文通过一种基于学习方法的超分辨率重建来提高视频的分辨率。与静态图像的超分辨率重建不同,视频的超分辨率重建以运动信息的应用为特征。但是,到目前为止,这方面的研究很少。旨在全面探索运动信息以改善视频的超分辨率,本文提出了一种基于高效亚像素卷积神经网络的超分辨率重建方法,其中将光流引入了深度学习网络。在连续的帧之间融合光流特征可以补偿帧中的信息并生成高质量的超分辨率结果。另外,为了改善超分辨率,在深度卷积网络之后添加了超像素卷积层。最后,实验评估表明,与以前的方法和其他深度学习网络相比,我们的方法具有令人满意的性能;我们的方法更有效。在连续的帧之间融合光流特征可以补偿帧中的信息并生成高质量的超分辨率结果。另外,为了改善超分辨率,在深度卷积网络之后添加了超像素卷积层。最后,实验评估表明,与以前的方法和其他深度学习网络相比,我们的方法具有令人满意的性能;我们的方法更有效。在连续的帧之间融合光流特征可以补偿帧中的信息并生成高质量的超分辨率结果。另外,为了提高超分辨率,在深度卷积网络之后添加了超像素卷积层。最后,实验评估表明,与以前的方法和其他深度学习网络相比,我们的方法具有令人满意的性能;我们的方法更有效。
更新日期:2020-07-13
down
wechat
bug